arXiv subjects

Haozhen Li

Publications and source records attributed to Haozhen Li.

13 recordsLinked to original sources

arXiv2026

SoM-MTM: Synesthesia of Machines (SoM)-Driven Masked Token Model for Cooperative Perception over Packet Loss Channel

To support the large-scale and heterogeneous visual cooperative perception (CP) demands in next-generation mobile networks, intelligent and efficient sensory data transmission is a critical challenge. Under the emerging convergence of communication networks and agentic artificial intelligence (AI), existing research emphasizes utilizing end-to-end neural networks to simplify communication modules, which has shown promising potential for CP. However, these studies are still limited to specific channel models, cooperation modes, and perception tasks, failing to fully leverage powerful visual processing approaches to enhance universality. To address this, we propose a Synesthesia of Machines (SoM)-driven Masked Token Model, referred to as SoM-MTM, as a plug-and-play paradigm for generic visual CP. Inspired by masked image modeling methods such as MAE, it possesses great perceptual context learning capabilities to recover distorted features over packet loss channels, thereby improving information carrying efficiency. Building upon Swin Transformer, SoM-MTM further embeds prior masked information through an External Routing MoE mechanism, maximally repairing and enhancing environmental perception features during cooperation. Comprehensive experimental results confirm that SoM-MTM can consistently enhance perception performances on various tasks, especially strong generalization to unseen scenarios, while maintaining favorable model cost and scalability.

eess.IV↗

arXiv2026

ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents

Memory-augmented language agents are increasingly deployed in affective applications such as emotional support, where understanding and responding to users' latent emotional needs is critical. However, existing research often treats memory as a tool for factual retrieval, overlooking its role in shaping users' emotional experiences. In this work, we introduce ENPMR-Bench, a benchmark for evaluating Emotional Need-aware Proactive Memory Retrieval (ENPMR), a core capability that enables agents to infer users' latent emotional needs and proactively retrieve appropriate memories to support empathetic interaction. Grounded in Maslow's hierarchy of needs, ENPMR-Bench includes over 1,800 memory-augmented dialogues and defines structured mappings between emotional needs and supportive memory types. Experimental results demonstrate that current retrieval paradigms, including both embedding-based and LLM-driven approaches, exhibit substantial deficiencies, with empathy scores significantly lagging behind golden memory conditions. While chain-of-thought prompting improves the alignment between inferred emotional needs and retrieved memories to some extent, a notable performance gap remains. Together, these findings reveal critical limitations in current agents and outline directions for advancing personalized emotional support through need-sensitive memory retrieval.

cs.CL↗

arXiv2026

ConflictBench: Evaluating Human-AI Conflict via Interactive and Visually Grounded Environments

As large language models (LLMs) evolve into autonomous agents capable of acting in open-ended environments, ensuring behavioral alignment with human values becomes a critical safety concern. Existing benchmarks, focused on static, single-turn prompts, fail to capture the interactive and multi-modal nature of real-world conflicts. We introduce ConflictBench, a benchmark for evaluating human-AI conflict through 150 multi-turn scenarios derived from prior alignment queries. ConflictBench integrates a text-based simulation engine with a visually grounded world model, enabling agents to perceive, plan, and act under dynamic conditions. Empirical results show that while agents often act safely when human harm is immediate, they frequently prioritize self-preservation or adopt deceptive strategies in delayed or low-risk settings. A regret test further reveals that aligned decisions are often reversed under escalating pressure, especially with visual input. These findings underscore the need for interaction-level, multi-modal evaluation to surface alignment failures that remain hidden in conventional benchmarks.

cs.CL↗

arXiv2025

OPOR-Bench: Evaluating Large Language Models on Online Public Opinion Report Generation

Online Public Opinion Reports consolidate news and social media for timely crisis management by governments and enterprises. While large language models have made automated report generation technically feasible, systematic research in this specific area remains notably absent, particularly lacking formal task definitions and corresponding benchmarks. To bridge this gap, we define the Automated Online Public Opinion Report Generation (OPOR-GEN) task and construct OPOR-BENCH, an event-centric dataset covering 463 crisis events with their corresponding news articles, social media posts, and a reference summary. To evaluate report quality, we propose OPOR-EVAL, a novel agent-based framework that simulates human expert evaluation by analyzing generated reports in context. Experiments with frontier models demonstrate that our framework achieves high correlation with human judgments. Our comprehensive task definition, benchmark dataset, and evaluation framework provide a solid foundation for future research in this critical domain.

cs.CL↗

arXiv2025

Synesthesia of Machines (SoM)-Empowered Wireless Image Transmission over Complex Dynamic Channel

Wireless image transmission underpins diverse networked intelligent services and becomes an increasingly critical issue. Existing works have shown that deep learning-based joint source-channel coding (JSCC) is an effective framework to balance image transmission fidelity and data overhead. However, these studies oversimplify the communication system as a mere pipeline with noise, failing to account for the complex dynamics of wireless channels and concrete physical-layer transmission process. To address these limitations, we propose a Synesthesia of Machines (SoM)-empowered Dynamic Channel Adaptive Transmission (DCAT) scheme, designed for practical implementation in real communication scenarios. Building upon the Swin Transformer backbone, our DCAT scheme demonstrates robust adaptability to time-selective fading and channel aging effects by effectively utilizing the physical-layer transmission characteristics of wireless channels. Comprehensive experimental results confirm that DCAT consistently achieves superior performance compared with JSCC baseline approaches across all conditions. Furthermore, our neural network architecture demonstrates high scalability due to its interpretable design, offering substantial potential for cost-efficient deployment in practical applications.

eess.SP↗

arXiv2025

OpenTie: Open-vocabulary Sequential Rebar Tying System

Robotic practices on the construction site emerge as an attention-attracting manner owing to their capability of tackling complex challenges, especially in the rebar-involved scenarios. Most of existing products and research are mainly focused on the collection of large amounts of data with model training demands. To fulfill this gap, we propose OpenTie, a 3D training-free rebar tying framework utilizing a RGB-to-point-cloud generation and an open-vocabulary rebar detection on the real-world test. We implement the OpenTie via a robotic arm with a binocular camera and guarantee a high accuracy by applying the prompt-based object detection method on the image filtered by our proposed post-processing procedure for the image-to-point-cloud generation framework. Our pipeline requires no training efforts and outperforms the training-based object detection, i.e., YOLO-based method, with the verification on the real-world sequential rebar tying test. The system is flexible for horizontal and vertical rebar tying tasks and holds the potential application to the real construction site with possibility of commercialization.

cs.RO↗

arXiv2024

A CSI Feedback Framework based on Transmitting the Important Values and Generating the Others

The application of deep learning (DL)-based channel state information (CSI) feedback frameworks in massive multiple-input multiple-output (MIMO) systems has significantly improved reconstruction accuracy. However, the limited generalization of widely adopted autoencoder-based networks for CSI feedback challenges consistent performance under dynamic wireless channel conditions and varying communication overhead constraints. To enhance the robustness of DL-based CSI feedback across diverse channel scenarios, we propose a novel framework, ITUG, where the user equipment (UE) transmits only a selected portion of critical values in the CSI matrix, while a generative model deployed at the BS reconstructs the remaining values. Specifically, we introduce a scoring algorithm to identify important values based on amplitude and contrast, an encoding algorithm to convert these values into a bit stream for transmission using adaptive bit length and a modified Huffman codebook, and a Transformer-based generative network named TPMVNet to recover the untransmitted values based on the received important values. Experimental results demonstrate that the ITUG framework, equipped with a single TPMVNet, achieves superior reconstruction performance compared to several high-performance autoencoder models across various channel conditions.

eess.SP↗

arXiv2024

Csi-LLM: A Novel Downlink Channel Prediction Method Aligned with LLM Pre-Training

Downlink channel temporal prediction is a critical technology in massive multiple-input multiple-output (MIMO) systems. However, existing methods that rely on fixed-step historical sequences significantly limit the accuracy, practicality, and scalability of channel prediction. Recent advances have shown that large language models (LLMs) exhibit strong pattern recognition and reasoning abilities over complex sequences. The challenge lies in effectively aligning wireless communication data with the modalities used in natural language processing to fully harness these capabilities. In this work, we introduce Csi-LLM, a novel LLM-powered downlink channel prediction technique that models variable-step historical sequences. To ensure effective cross-modality application, we align the design and training of Csi-LLM with the processing of natural language tasks, leveraging the LLM's next-token generation capability for predicting the next step in channel state information (CSI). Simulation results demonstrate the effectiveness of this alignment strategy, with Csi-LLM consistently delivering stable performance improvements across various scenarios and showing significant potential in continuous multi-step prediction.

cs.IT↗

arXiv2023

Dig-CSI: A Distributed and Generative Model Assisted CSI Feedback Training Framework

The advent of deep learning (DL)-based models has significantly advanced Channel State Information (CSI) feedback mechanisms in wireless communication systems. However, traditional approaches often suffer from high communication overhead and potential privacy risks due to the centralized nature of CSI data processing. To address these challenges, we design a CSI feedback training framework called Dig-CSI, in which the dataset for training the CSI feedback model is produced by the distributed generators uploaded by each user equipment (UE), but not through local data upload. Each UE trains an autoencoder, where the decoder is considered as the distributed generator, with local data to gain reconstruction accuracy and the ability to generate. Experimental results show that Dig-CSI can train a global CSI feedback model with comparable performance to the model trained with classical centralized learning with a much lighter communication overhead.

cs.AI↗

arXiv2023

HybridCVLNet: A Hybrid CSI Feedback System and its Domain Adaptation

Deep Learning (DL)-based channel state information (CSI) feedback is a promising technique for the transmitter to accurately acquire the CSI of massive multiple-input multiple-output (MIMO) systems. As critical concerns about DL-based physical layer applications, the intra-domain generalizability affected by dataset bias and inter-domain robustness in data drift remain challenging. Therefore, we build on a Hybrid Complex-Valued Lightweight framework, namely the HybridCVLNet, capable of overcoming the dataset bias with regularized hybrid structure and codeword. Meanwhile, a corresponding transductive-based hybrid domain adaptation scheme is proposed to tackle the inter-domain data drift. The experiment verifies that HybridCVLNet achieves stable generalizability and performance gain over the state-of-the-art (SOTA) feedback schemes in an intra-domain heterogeneous dataset. In addition, its transductive-based hybrid domain adaptation scheme is more efficient and superior to the inductive-based transfer learning methods under two inter-domain online re-optimization settings.

eess.SP↗

arXiv2022

Multi-task Deep Neural Networks for Massive MIMO CSI Feedback

Deep learning has been widely applied for the channel state information (CSI) feedback in frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) system. For the typical supervised training of the feedback model, the requirements of large amounts of task-specific labeled data can hardly be satisfied, and the huge training costs and storage usage of the model in multiple scenarios are hindrance for model application. In this letter, a multi-task learning-based approach is proposed to improve the feasibility of the feedback network. An encoder-shared feedback architecture and the corresponding training scheme are further proposed to facilitate the implementation of the multi-task learning approach. The experimental results indicate that the proposed multi-task learning approach can achieve comprehensive feedback performance with considerable reduction of training cost and storage usage of the feedback model.

cs.IT↗

arXiv2022

Changeable Rate and Novel Quantization for CSI Feedback Based on Deep Learning

Deep learning (DL)-based channel state information (CSI) feedback improves the capacity and energy efficiency of massive multiple-input multiple-output (MIMO) systems in frequency division duplexing mode. However, multiple neural networks with different lengths of feedback overhead are required by time-varying bandwidth resources. The storage space required at the user equipment (UE) and the base station (BS) for these models increases linearly with the number of models. In this paper, we propose a DL-based changeable-rate framework with novel quantization scheme to improve the efficiency and feasibility of CSI feedback systems. This framework can reutilize all the network layers to achieve overhead-changeable CSI feedback to optimize the storage efficiency at the UE and the BS sides. Designed quantizer in this framework can avoid the normalization and gradient problems faced by traditional quantization schemes. Specifically, we propose two DL-based changeable-rate CSI feedback networks CH-CsiNetPro and CH-DualNetSph by introducing a feedback overhead control unit. Then, a pluggable quantization block (PQB) is developed to further improve the encoding efficiency of CSI feedback in an end-to-end way. Compared with existing CSI feedback methods, the proposed framework saves the storage space by about 50% with changeable-rate scheme and improves the encoding efficiency with the quantization module.

cs.IT↗

arXiv2021

CSI Sensing and Feedback: A Semi-Supervised Learning Approach

Deep learning-based (DL-based) channel state information (CSI) feedback for a Massive multiple-input multiple-output (MIMO) system has proved to be a creative and efficient application. However, the existing systems ignored the wireless channel environment variation sensing, e.g., indoor and outdoor scenarios. Moreover, systems training requires excess pre-labeled CSI data, which is often unavailable. In this letter, to address these issues, we first exploit the rationality of introducing semi-supervised learning on CSI feedback, then one semi-supervised CSI sensing and feedback Network ($S^2$CsiNet) with three classifiers comparisons is proposed. Experiment shows that $S^2$CsiNet primarily improves the feasibility of the DL-based CSI feedback system by \textbf{\textit{indoor}} and \textbf{\textit{outdoor}} environment sensing and at most 96.2\% labeled dataset decreasing and secondarily boost the system performance by data distillation and latent information mining.

eess.SP↗